Unmanned aerial vehicle low-altitude network communication management method based on 5G and internet of things

Abstract

The application relates to a 5G and Internet of Things based unmanned aerial vehicle low-altitude network communication management method, which relates to the technical field of communication control and comprises the following steps: an unmanned aerial vehicle selects a 5G network slice to construct a virtual network, sets network slice bandwidth according to an assigned task, simultaneously selects multiple available network slices, and presets bandwidth resources of the network slices according to the task; the unmanned aerial vehicle performs aerial testing and evaluation, monitors and calculates a communication environment, selects network slices capable of successfully completing the task by taking transmission power as a judgment standard, connects the network slices and executes a flight task, dynamically adjusts communication parameters in the network slices, makes the unmanned aerial vehicle be in the best parameter configuration to provide better communication quality, and automatically switches the network slices according to the communication parameter adjustment result, so that the performance of the network slices is fully exerted and the stability of connection is ensured through the network slice screening and real-time adjustment of the communication parameters.

Description

Technical Field

[0001] This invention relates to the field of communication control technology, specifically to a method for managing low-altitude network communication of unmanned aerial vehicles (UAVs) based on 5G and the Internet of Things. Background Technology

[0002] With the increasing application of drones in various fields, real-time data transmission and communication quality have become critical issues. Traditional communication networks often cannot meet the drones' requirements for low latency and high bandwidth, and are particularly susceptible to interference in complex environments, leading to unstable data transmission. In addition, fixed communication parameter settings often cannot adapt to dynamically changing environments, further affecting communication quality. Existing technologies mainly rely on improving network hardware performance or increasing transmission power to address these challenges, but these methods cannot fundamentally solve the problems and increase energy consumption and costs.

[0003] According to the communication quality improvement method, apparatus, and medium for low-altitude communication of unmanned aerial vehicle (UAV) terminals disclosed in CN202210960796.X, the method includes: assigning a dedicated 5G mobile communication technology (5QI) quality of service identifier to the UAV terminal; adjusting the handover parameters of the UAV terminal with the assigned 5QI value in a 5G public network, wherein the adjusted handover parameters of the UAV terminal are greater than the handover parameters corresponding to user terminals in the 5G public network; and sending the 5QI value and the adjusted handover parameters to the UAV terminal so that the UAV terminal can handover according to the 5QI value and the adjusted handover parameters.

[0004] While the aforementioned patent enables drones to switch networks based on 5G, the method for judging the switching is too simplistic and does not fully utilize the performance of network slicing. Using a single evaluation criterion can easily lead to wasted network performance and frequent switching, thereby affecting connection stability. Summary of the Invention

[0005] (a) Technical problems to be solved

[0006] To address the shortcomings of existing technologies, this invention provides a method for managing low-altitude network communication for unmanned aerial vehicles (UAVs) based on 5G and the Internet of Things (IoT). During the test flight of the UAV, multiple data such as signal strength and loss are detected and introduced. In the actual mission execution, multiple communication parameters are adjusted and optimized in real time through reinforcement learning to fully ensure the stability of the connection side.

[0007] (II) Technical Solution

[0008] To achieve the above objectives, the present invention provides the following technical solution:

[0009] A method for managing low-altitude network communication for drones based on 5G and the Internet of Things, comprising the following steps:

[0010] Step 1: The drone selects a 5G network slice to build a virtual network and sets the network slice bandwidth according to the assigned task;

[0011] Step 2: The drone conducts aerial testing and evaluation, and selects network slices that can successfully complete the mission based on the communication environment;

[0012] Step 3: The drone connects to the network slice and performs flight missions, dynamically adjusting its communication parameters within the network slice;

[0013] Step 4: The drone automatically switches network slices based on the communication parameter adjustment results.

[0014] Furthermore, the logic for the drone selecting 5G network slices to construct a virtual network and setting network slice bandwidth according to the assigned tasks is as follows: the drone initially selects network slices based on the bandwidth, latency, and QoS required to perform the tasks, sets the number of tasks the drone needs to perform and the weight of each task in the overall task, and allocates network slice bandwidth resources according to these task weights. The formula used is:

[0015]

[0016] R i This is the bandwidth allocated to task i;

[0017] W i It is the weight of task i, reflecting its priority;

[0018] It is the sum of the weights of all tasks;

[0019] n is the total number of tasks;

[0020] R is the total bandwidth of the network slice;

[0021] In step 1, more than one network slice is selected, and the bandwidth allocation is preset in the same way for all selected network slices.

[0022] Further, step 2 involves aerial testing and evaluation of the UAV. Based on the communication environment, network slices suitable for successful mission completion are selected. The UAV is then test-flown, and communication environment data is monitored. This data includes the signal strength received by the UAV, the distance between the UAV and the base station, and the signal frequency. A spectrum analyzer is used to obtain the reflection, refraction, and diffraction losses, phase noise power, and background noise power between the UAV and the base station. A multipath signal analyzer detects the loss caused by multipath effects. A signal strength testing instrument determines the penetration loss by detecting changes in signal strength after the UAV encounters different obstacles. Signal strength, signal-to-noise ratio, and delay are calculated to evaluate the current UAV communication performance in the current environment. The formula for RSSI (Representative Signal Strength Index) is as follows:

[0023] RSSI = P received -P loss

[0024] FSPL = 20log 10 (d)+20log 10 (f)+20log 10 (4π / c)

[0025] P loss =FSPL+FZ+DS+CS

[0026] Among them, P received It is the signal strength received by the drone, P loss RSSI is the power loss experienced by the signal during propagation. FSPL is the free space path loss, d is the communication distance, f is the signal frequency, and c is the speed of light. d, f, and c are dimensionless. FZ is the reflection, refraction, and diffraction loss, DS is the multipath effect loss, and CS is the penetration loss. When the RSSI value is higher than -70dBm, the communication quality is considered to be good and the signal strength is high, which can meet the current communication requirements. Otherwise, the signal strength is considered not to meet the communication requirements, and the signal transmission power is increased to improve the signal strength.

[0027] The signal-to-noise ratio (SNR) is based on the following formula, obtained by measuring phase noise and ambient background noise using a spectrum analyzer:

[0028]

[0029] N = kTB

[0030] P signal Here, N is the signal power, k is the Boltzmann constant, T is the absolute temperature of the environment, B is the bandwidth, XZ-type phase noise power, and BZ is the background noise power.

[0031] When SNR>25dB, it is considered that the signal-to-noise ratio required for communication is met; otherwise, it is considered that the signal-to-noise ratio required for communication is not met, and the transmission power is increased to enhance the signal reception effect.

[0032] The formula for latency is as follows:

[0033] Latency = T received -T sent

[0034] Among them, T received It is the data packet arrival time, T sent This refers to the data packet transmission time. If the latency is less than 10ms, it is considered to meet the latency required for communication. Otherwise, the latency is considered to be too high and does not meet the communication requirements. In this case, the transmission power is increased to reduce the latency.

[0035] Increasing the transmit power allows the signal strength, signal-to-noise ratio, and delay to all meet communication requirements. This relates to the transmit power P under the condition that the communication requirements are met. fs Make a judgment when P fs >2 / 3P za If it is determined that the current network slice cannot enable the UAV to successfully complete its mission, then a new network slice is switched. fs ≤2 / 3P za At that time, it was determined that this network slice would enable the drone to successfully complete its mission. za This represents the maximum transmit power of the base station.

[0036] Step 2 involves selecting all network slices from Step 1, retaining the slices that enable the drone to successfully complete its mission, and removing network slices that do not enable the drone to successfully complete its mission.

[0037] Further, step 3 involves the UAV connecting to a network slice and executing a flight mission, dynamically adjusting its communication parameters within the network slice. The UAV selects a network slice from step 2, with the remaining slices used as backups. The UAV performs the flight mission and adjusts the communication parameters within the network slice in real time. The communication parameters recorded by the UAV include signal strength, bandwidth utilization, and interference intensity. The signal strength and interference intensity are then processed to be dimensionless. A dynamic learning method is used to adjust the communication parameters, and the reward function is set as follows:

[0038] R = α·RSSI + β·B - γ·P loss

[0039] R is the instant reward, RSSI is the signal strength, B is the bandwidth utilization, and P is the signal strength. loss The value represents the interference intensity, and α, β, and γ are weighting coefficients, where α>0, β>0, and γ>0.

[0040] The parameter adjustment actions include increasing transmit power a1, switching modulation mode a2, switching antenna mode a3, and increasing bandwidth a4. In the initial state s1, the Q(s1,a) value for each action is set. y The values ​​are all 0, and then Q-learning reinforcement learning is performed to determine the state of the current communication parameters. i Next, select an action a. y The communication system's state transitions to the next state s. i+1 And generate an immediate reward R based on the new state in the next state s. i+1 Select the action with the largest Q value, update the current state using a weighted calculation, and then perform action a. y The Q-value is calculated, and the Q-value generated by each action in each state is continuously updated and recorded in a Q-table, based on the following formula:

[0041]

[0042] α is the learning rate, α>0, R is the immediate reward, γ is the discount factor, γ>0, s i+1 For the new state reached after performing the action, Q(s) i ,a y ) indicates that in state s i Next, execute action a y Let Q be the value of the action, i represent the retrieval variable of the state sequence, i∈N, and y represent the retrieval variable of the action, y∈N and 1≤y≤3. Indicates the next state s i+1 The maximum Q value generated among all actions is determined by setting the next state s before performing the first action. i+1 The maximum Q value is set to 0, Q new (s i ,a y ) represents the updated state s i Perform a y Q value, Q old (s i ,a y ) represents the state s before the update. i Perform a y Q value;

[0043] When the Q-value update magnitude is less than 0.01, the current communication parameters are considered to be in the optimal state, and the transmit power, modulation method, antenna mode, and bandwidth are set according to this state. Otherwise, training and learning continue to cope with the real-time changing environment. When the transmit power is greater than 100% or the total bandwidth of all tasks exceeds the maximum allowable bandwidth of this network slice while the Q-value update is still greater than 0.01, the network slice is switched.

[0044] Furthermore, in the Q-learning reinforcement learning process, an ε-greedy strategy is used to select actions to continuously reduce the Q-value update magnitude. An ε value is artificially set within the (0,1) interval. An action is randomly selected with probability ε for Q-value update, while the action with the highest Q-value in the current state is selected with probability 1-ε for Q-value update. Each time an action is selected, ε decreases. The formula used is:

[0045] ∈ t =∈0e -λt

[0046] λ is a parameter controlling the deceleration rate; λ>0, ∈0 is the initial setpoint, ∈ t The value after t actions.

[0047] Further, step 4 involves the UAV automatically switching network slices based on the communication parameter adjustment results. During step 3, after determining the need to switch network slices, the UAV does not disconnect from the current network slice. While maintaining the current network slice, the UAV connects to another network slice, allowing the UAV to connect to two network slices simultaneously. The current network slice is designated as network slice I, and the other network slice is designated as network slice II. The UAV collects the state data from network slice I that has undergone reinforcement learning and moves it to network slice II. The state data includes the current transmit power, modulation scheme, antenna mode, bandwidth, and Q table. Step 3 is then executed in network slice II to determine whether network slice II can obtain the optimal state of communication parameters. If network slice II obtains the optimal state of communication parameters, the transmit power, modulation scheme, antenna mode, and bandwidth of network slice II are set according to the optimal state. The connection of network slice I is then disconnected, and all traffic is redirected to network slice II that meets the conditions.

[0048] When network slice II also indicates that a network slice needs to be switched, another backup network slice is used as the new network slice II to perform state data transfer and step 3 again. All backup network slices are traversed until the optimal state of communication parameters is obtained. When the optimal state of communication parameters cannot be obtained by traversing all backup networks, the network slice with the smallest Q value update is selected as the best network slice and switched to that network slice.

[0049] (III) Beneficial Effects

[0050] This invention provides a method for managing low-altitude network communication for drones based on 5G and the Internet of Things. By screening network slices through missions and test flights, it prepares the drone for mission execution. At the same time, during the drone mission execution, it continuously improves the connection performance between the drone and the base station through reinforcement learning, giving full play to the performance of network slices and ensuring connection stability. Attached Figure Description

[0051] Figure 1 This is a schematic diagram of the process of the present invention. Detailed Implementation

[0052] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] A method for managing low-altitude network communication for drones based on 5G and the Internet of Things, comprising the following steps:

[0054] Step 1: The drone selects a 5G network slice to build a virtual network and sets the network slice bandwidth according to the assigned task;

[0055] In a preferred embodiment, the logic for the UAV to select a 5G network slice to construct a virtual network and to set the network slice bandwidth according to the assigned tasks is as follows: the UAV initially selects a network slice based on the bandwidth, latency, and QoS required to perform the tasks, sets the number of tasks the UAV needs to perform and the weight of each task in the overall tasks, and allocates the bandwidth resources of the network slice according to these task weights. The formula used is:

[0056]

[0057] R i This is the bandwidth allocated to task i;

[0058] W i It is the weight of task i, reflecting its priority;

[0059] It is the sum of the weights of all tasks;

[0060] n is the total number of tasks;

[0061] R is the total bandwidth of the network slice;

[0062] In step 1, more than one network slice is selected, and the bandwidth allocation is preset in the same way for all selected network slices.

[0063] By initially selecting multiple network slices, the optimal network slice is selected, which prepares the UAV for switching network slices during mission execution. At the same time, the initially set slices are all available network slices that can meet all UAV missions, which provides a guarantee for the automatic switching of network slices in step 4, avoids fluctuations in network slices during the switching process and possible verification failures, and ensures the stability of the connection performance.

[0064] Step 2: The drone conducts aerial testing and evaluation, and selects network slices that can successfully complete the mission based on the communication environment;

[0065] In a preferred embodiment, the UAV is test-flown, and communication environment data is monitored. This data includes the signal strength received by the UAV, the distance between the UAV and the base station, and the signal frequency. A spectrum analyzer is used to obtain the reflection, refraction, and diffraction losses, phase noise power, and background noise power between the UAV and the base station. A multipath signal analyzer detects the loss caused by multipath effects. A signal strength detection instrument determines the penetration loss by detecting changes in the UAV's signal strength behind different obstacles. Signal strength, signal-to-noise ratio (SNR), and delay are calculated to evaluate the current UAV communication performance in the current environment. The formula for the RSSI signal strength is as follows:

[0066] RSSI = P received -P loss

[0067] FSPL = 20log 10 (d)+20log 10 (f)+20log 10 (4π / c)

[0068] P loss =FSPL+FZ+DS+CS

[0069] Among them, P received It is the signal strength received by the drone, P loss RSSI is the power loss experienced by the signal during propagation. FSPL is the free space path loss, d is the communication distance, f is the signal frequency, and c is the speed of light. d, f, and c are dimensionless. FZ is the reflection, refraction, and diffraction loss, DS is the multipath effect loss, and CS is the penetration loss. When the RSSI value is higher than -70dBm, the communication quality is considered to be good and the signal strength is high, which can meet the current communication requirements. Otherwise, the signal strength is considered not to meet the communication requirements, and the signal transmission power is increased to improve the signal strength.

[0070] The signal-to-noise ratio (SNR) is based on the following formula, obtained by measuring phase noise and ambient background noise using a spectrum analyzer:

[0071]

[0072] N = kTB

[0073] P signal Here, N is the signal power, k is the Boltzmann constant, T is the absolute temperature of the environment, B is the bandwidth, XZ-type phase noise power, and BZ is the background noise power.

[0074] When SNR>25dB, it is considered that the signal-to-noise ratio required for communication is met; otherwise, it is considered that the signal-to-noise ratio required for communication is not met, and the transmission power is increased to enhance the signal reception effect.

[0075] The formula for latency is as follows:

[0076] Latency = T received -T sent

[0077] Among them, T received It is the data packet arrival time, T sent This refers to the data packet transmission time. If the latency is less than 10ms, it is considered to meet the latency required for communication. Otherwise, the latency is considered to be too high and does not meet the communication requirements. In this case, the transmission power is increased to reduce the latency.

[0078] Increasing the transmit power allows the signal strength, signal-to-noise ratio, and delay to all meet communication requirements. This relates to the transmit power P under the condition that the communication requirements are met. fs Make a judgment when P fs >2 / 3P za If it is determined that the current network slice cannot enable the UAV to successfully complete its mission, then a new network slice is switched. fs ≤2 / 3P za At that time, it was determined that this network slice would enable the drone to successfully complete its mission. za This represents the maximum transmit power of the base station.

[0079] Step 2 involves selecting all network slices from Step 1, retaining the slices that enable the drone to successfully complete its mission, and removing network slices that do not enable the drone to successfully complete its mission.

[0080] During the test flight, by collecting and analyzing signal strength, signal-to-noise ratio, and delay parameters in real time, each network slice selected in step 1 will be judged to obtain network slices with excellent connection performance. At the same time, preparations will be made for the automatic switching of UAV network slices to ensure smooth connection.

[0081] Step 3: The drone connects to the network slice and performs flight missions, dynamically adjusting its communication parameters within the network slice;

[0082] In a preferred embodiment, the UAV selects a network slice from step 2, with the remaining network slices as backups. The UAV performs flight missions and adjusts the communication parameters within the network slices in real time. The communication parameters recorded by the UAV include signal strength, bandwidth utilization, and interference intensity. The signal strength and interference intensity are then processed to be dimensionless. A dynamic learning method is used to adjust the communication parameters, and the reward function is set as follows:

[0083] R = α·RSSI + β·B - γ·Ploss

[0084] R is the instant reward, RSSI is the signal strength, B is the bandwidth utilization, and P is the signal strength. loss The value represents the interference intensity, and α, β, and γ are weighting coefficients, where α>0, β>0, and γ>0.

[0085] The parameter adjustment actions include increasing transmit power a1, switching modulation mode a2, switching antenna mode a3, and increasing bandwidth a4. In the initial state s1, the Q(s1,a) value for each action is set. y The values ​​are all 0, and then Q-learning reinforcement learning is performed to determine the state of the current communication parameters. i Next, select an action a. y The communication system's state transitions to the next state s. i+1 And generate an immediate reward R based on the new state in the next state s. i+1 Select the action with the largest Q value, update the current state using a weighted calculation, and then perform action a. y The Q-value is calculated, and the Q-value generated by each action in each state is continuously updated and recorded in a Q-table, based on the following formula:

[0086]

[0087] α is the learning rate, α>0, R is the immediate reward, γ is the discount factor, γ>0, s i+1 For the new state reached after performing the action, Q(s) i ,a y ) indicates that in state s i Next, execute action a y Let Q be the value of the action, i represent the retrieval variable of the state sequence, i∈N, and y represent the retrieval variable of the action, y∈N and 1≤y≤3. Indicates the next state s i+1 The maximum Q value generated among all actions is determined by setting the next state s before performing the first action. i+1 The maximum Q value is set to 0, Q new (s i ,a y ) represents the updated state s i Perform a y Q value, Q old (s i ,a y ) represents the state s before the update. i Perform a y Q value;

[0088] When the Q-value update magnitude is less than 0.01, the current communication parameters are considered to be in the optimal state, and the transmit power, modulation method, antenna mode, and bandwidth are set according to this state. Otherwise, training and learning continue. When the transmit power is greater than 100% or the total bandwidth of all tasks exceeds the maximum allowable bandwidth of this network slice while the Q-value update is still greater than 0.01, the network slice is switched.

[0089] In a preferred embodiment, during Q-learning reinforcement learning, an ε-greedy strategy is used to select actions to continuously reduce the Q-value update magnitude. An ε value is manually set within the (0,1) interval. An action is randomly selected with probability ε for Q-value update, while simultaneously selecting the action with the highest Q-value in the current state with probability 1-ε for Q-value update. Furthermore, ε decreases with each action selection, based on the following formula:

[0090] ∈ t =∈0e -λt

[0091] λ is a parameter controlling the deceleration rate; λ>0, ∈0 is the initial setpoint, ∈ t The value after t actions.

[0092] Through dynamic adaptive adjustment using reinforcement learning, drones can automatically optimize state data in different environments and continuously optimize communication connection performance within network slices during mission execution, ensuring stable and efficient data transmission. By optimizing within network slices that already have connectivity, the quality of communication connections is further improved.

[0093] Step 4: The drone automatically switches network slices based on the communication parameter adjustment results.

[0094] In a preferred embodiment, after determining the need to switch network slices in step 3, the UAV does not disconnect from the current network slice. While maintaining the current network slice, the UAV connects to another network slice, allowing the UAV to connect to two network slices simultaneously. The current network slice is designated as network slice I, and the other network slice is designated as network slice II. The UAV collects the state data that has undergone reinforcement learning in network slice I and moves it to network slice II. The state data includes the current transmit power, modulation scheme, antenna mode, bandwidth, and Q table. Step 3 is then executed in network slice II to determine whether network slice II can obtain the optimal state of communication parameters. If network slice II obtains the optimal state of communication parameters, the transmit power, modulation scheme, antenna mode, and bandwidth of network slice II are set according to the optimal state. The connection of network slice I is then disconnected, and all traffic is redirected to network slice II that meets the conditions.

[0095] When network slice II also indicates that a network slice needs to be switched, another backup network slice is used as the new network slice II to perform state data transfer and step 3 again. All backup network slices are traversed until the optimal state of communication parameters is obtained. When the optimal state of communication parameters cannot be obtained by traversing all backup networks, the network slice with the smallest Q value update is selected as the best network slice and switched to that network slice.

[0096] By maintaining the connection of one network slice while calculating the internal parameters of the second network slice connection, the uninterrupted connection of the drone is ensured, while the short-term dual network slice connection also saves energy consumption.

[0097] The above formulas are all dimensionless calculations. The formulas are derived from software simulations using a large amount of collected data, and are the closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0098] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0099] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for managing low-altitude network communication of unmanned aerial vehicles (UAVs) based on 5G and the Internet of Things, characterized by the following steps: include: Step 1: The drone selects a 5G network slice to build a virtual network and sets the network slice bandwidth according to the assigned task; The logic for drones selecting 5G network slices to construct virtual networks and allocating network slice bandwidth according to assigned tasks is as follows: The drone initially selects network slices based on the bandwidth, latency, and QoS required for the tasks, sets the number of tasks the drone needs to perform and the weight of each task within the overall task load, and allocates network slice bandwidth resources based on these task weights. The formula used is: R i This is the bandwidth allocated to task i; W i It is the weight of task i, reflecting its priority; It is the sum of the weights of all tasks; n is the total number of tasks; R is the total bandwidth of the network slice; In step 1, the number of network slices selected is not just one, and the bandwidth allocation of all selected network slices is preset in the same way. Step 2: The drone conducts aerial testing and evaluation, and selects network slices that can successfully complete the mission based on the communication environment; Step 2 involves aerial testing and evaluation of the UAV. Based on the communication environment, network slices suitable for successful mission completion are selected. The UAV is then test-flown, and communication environment data is monitored. This data includes the signal strength received by the UAV, the distance between the UAV and the base station, and the signal frequency. A spectrum analyzer is used to obtain the reflection, refraction, and diffraction losses, phase noise power, and background noise power between the UAV and the base station. A multipath signal analyzer detects the loss caused by multipath effects. A signal strength testing instrument determines the penetration loss by detecting changes in signal strength after the UAV encounters different obstacles. Signal strength, signal-to-noise ratio (SNR), and delay are calculated to evaluate the current UAV communication performance in the current environment. The RSSI (Representative Signal Strength Index) formula is as follows: RSSI=P received -P loss FSPL=20log 10 (d)+20log 10 (f)+20log 10 (4π / c) P loss =FSPL+FZ+DS+CS Among them, P received It is the signal strength received by the drone, P loss RSSI is the power loss experienced by the signal during propagation. FSPL is the free space path loss, d is the communication distance, f is the signal frequency, and c is the speed of light. d, f, and c are dimensionless. FZ is the reflection, refraction, and diffraction loss, DS is the multipath effect loss, and CS is the penetration loss. When the RSSI value is higher than -70dBm, the communication quality is considered to be good and the signal strength is high, which can meet the current communication requirements. Otherwise, the signal strength is considered not to meet the communication requirements, and the signal transmission power is increased to improve the signal strength. The signal-to-noise ratio (SNR) is based on the following formula, obtained by measuring phase noise and ambient background noise using a spectrum analyzer: N = kTB P signal Here, N is the signal power, k is the Boltzmann constant, T is the absolute temperature of the environment, B is the bandwidth, XZ-type phase noise power, and BZ is the background noise power. When SNR>25dB, it is considered that the signal-to-noise ratio required for communication is met; otherwise, it is considered that the signal-to-noise ratio required for communication is not met, and the transmission power is increased to enhance the signal reception effect. The formula for latency is as follows: Latency=T received -T sent Among them, T received It is the data packet arrival time, T sent This refers to the data packet transmission time. If the latency is less than 10ms, it is considered to meet the latency required for communication. Otherwise, the latency is considered to be too high and does not meet the communication requirements. In this case, the transmission power is increased to reduce the latency. Increasing the transmit power allows the signal strength, signal-to-noise ratio, and delay to all meet communication requirements. This relates to the transmit power P under the condition that the communication requirements are met. fs Make a judgment when P fs >2 / 3P za If it is determined that the current network slice cannot enable the UAV to successfully complete its mission, then a new network slice is switched. fs ≤2 / 3P za At that time, it was determined that this network slice would enable the drone to successfully complete its mission. za This represents the maximum transmit power of the base station. Step 2 involves selecting all network slices from Step 1, retaining those that enable the drone to successfully complete its mission, and removing those that prevent the drone from doing so. Step 3: The drone connects to the network slice and performs flight missions, dynamically adjusting its communication parameters within the network slice; Step 3 involves the UAV connecting to a network slice and executing a flight mission, dynamically adjusting its communication parameters within the network slice. The UAV selects a network slice from step 2, with the remaining slices used as backups. The UAV performs the flight mission and adjusts the communication parameters within the network slice in real time. The communication parameters recorded by the UAV include signal strength, bandwidth utilization, and interference intensity. The signal strength and interference intensity are then processed to be dimensionless. A dynamic learning method is used to adjust the communication parameters, and the reward function is set as follows: R=α·RSSI+β·B-γ·P loss R is the instant reward, RSSI is the signal strength, B is the bandwidth utilization, and P is the signal strength. loss The value represents the interference intensity, and α, β, and γ are weighting coefficients, where α>0, β>0, and γ>0. The parameter adjustment actions include increasing transmit power a1, switching modulation mode a2, switching antenna mode a3, and increasing bandwidth a4. In the initial state s1, the Q(s1,a) value for each action is set. y The values ​​are all 0, and then Q-learning reinforcement learning is performed to determine the state of the current communication parameters. i Next, select an action a. y The communication system's state transitions to the next state s. i+1 And generate an immediate reward R based on the new state in the next state s. i+1 Select the action with the largest Q value, update the current state using a weighted calculation, and then perform action a. y The Q-value is calculated, and the Q-value generated by each action in each state is continuously updated and recorded in a Q-table, based on the following formula: α is the learning rate, α>0, R is the immediate reward, γ is the discount factor, γ>0, s i+1 For the new state reached after performing the action, Q(s) i ,a y ) indicates that in state s i Next, execute action a y Let Q be the value of the action, i represent the retrieval variable of the state sequence, i∈N, and y represent the retrieval variable of the action, y∈N and 1≤y≤3. Indicates the next state s i+1 The maximum Q value generated among all actions is determined by setting the next state s before performing the first action. i+1 The maximum Q value is set to 0, Q new (s i ,a y ) represents the updated state s i Perform a y Q value, Q old (s i ,a y ) represents the state s before the update. i Perform a y Q value; When the Q value update magnitude is less than 0.01, the communication parameters at that time are considered to be in the optimal state, and the transmit power, modulation method, antenna mode, and bandwidth are set according to this state. Otherwise, training and learning continue. When the transmit power is greater than 100% or the total bandwidth of all tasks exceeds the maximum allowable bandwidth of this network slice and the Q value update is still greater than 0.01, the network slice is switched. Step 4: The drone automatically switches network slices based on the communication parameter adjustment results.

2. The method for managing low-altitude network communication of unmanned aerial vehicles based on 5G and the Internet according to claim 1, characterized in that: In Q-learning reinforcement learning, an ε-greedy strategy is used to select actions to continuously reduce the Q-value update magnitude. An ε value is manually set within the (0,1) interval. An action is randomly selected with probability ε for Q-value update, while the action with the highest Q-value in the current state is selected with probability 1-ε for Q-value update. Each action selection decreases ε, based on the following formula: ∈ t ＝∈0e -λt λ is a parameter controlling the deceleration rate; λ>0, ∈0 is the initial setpoint, ∈ t The value after t actions.

3. The method for managing low-altitude network communication of unmanned aerial vehicles based on 5G and the Internet according to claim 2, characterized in that: Step 4 involves the UAV automatically switching network slices based on the communication parameter adjustment results. During step 3, after determining the need to switch network slices, the UAV does not disconnect from the current network slice. While maintaining the current network slice, the UAV connects to another network slice, allowing the UAV to connect to two network slices simultaneously. The current network slice is designated as network slice I, and the other network slice is designated as network slice II. The UAV collects the state data from network slice I that has undergone reinforcement learning and moves it to network slice II. The state data includes the current transmit power, modulation scheme, antenna mode, bandwidth, and Q table. Step 3 is then executed in network slice II to determine whether network slice II can obtain the optimal state of communication parameters. If network slice II obtains the optimal state of communication parameters, the transmit power, modulation scheme, antenna mode, and bandwidth of network slice II are set according to the optimal state. The connection of network slice I is then disconnected, and all traffic is redirected to network slice II that meets the conditions. When network slice II also indicates that a network slice needs to be switched, another backup network slice is used as the new network slice II to perform state data transfer and step 3 again. All backup network slices are traversed until the optimal state of communication parameters is obtained. When the optimal state of communication parameters cannot be obtained by traversing all backup networks, the network slice with the smallest Q value update is selected as the best network slice and switched to that network slice.

Images